Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1732 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0499. Min Range: -1.0499

Max Act: 1.0499. Min Act: -0.0001

Data Index: 450154 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.9322. Min Act: -0.0000

Data Index: 547692 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.9434. Min Act: -0.0001

Data Index: 183524 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8792. Min Act: -0.0001

Data Index: 750790 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8693. Min Act: -0.0000

Data Index: 111743 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8913. Min Act: -0.0000

Data Index: 77813 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1591974 (Python Code)

Max Activating Token Index: 266

Text #7

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.8745. Min Act: -0.0000

Data Index: 350838 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1311119 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7162. Min Act: -0.0000

Data Index: 297654 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7728. Min Act: -0.0000

Data Index: 899672 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6806. Min Act: -0.0000

Data Index: 695395 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7335. Min Act: -0.0000

Data Index: 274802 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.7528. Min Act: -0.0000

Data Index: 1120281 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6617. Min Act: -0.0000

Data Index: 335550 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6461. Min Act: -0.0000

Data Index: 776490 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1170472 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1646788 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6207. Min Act: -0.0000

Data Index: 996496 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 1.0499. Min Range: -1.0499

Max Act: 0.6092. Min Act: -0.0000

Data Index: 183674 (C4 (Web Text))

Max Activating Token Index: 157